INDEX

Explanations

scientific research papers

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èĢĨ

-0.26

 EventType

-0.26

Validity

-0.25

 Entrance

-0.25

ocols

-0.25

ìłĳ

-0.25

ç§¯æŀģåıĤä¸İ

-0.25

 VALID

-0.25

akra

-0.25

_paper

-0.24

POSITIVE LOGITS

 Incorporated

0.29

 spoilers

0.28

 equipped

0.26

Suppress

0.25

 spoiler

0.25

åģļèµ·

0.25

 ornament

0.24

 decorations

0.24

 encrypted

0.24

çĻ¾ç§ĳ

0.24

Activations Density 0.014%

scientific research papers

No Comments

No Known Activations