INDEX

Explanations

founders and owners

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

OM

-0.29

è¶Ĭ

-0.29

æģ¶

-0.27

”:

-0.27

ĳľ

-0.25

 tricks

-0.25

cut

-0.25

æĦĪ

-0.25

çĭ

-0.25

JM

-0.25

POSITIVE LOGITS

inski

0.29

èĵį

0.27

ä»£çĲĨ

0.27

ettle

0.26

 multiplier

0.26

å¹Ĥ

0.26

gage

0.26

dire

0.25

EDIA

0.25

-append

0.25

Activations Density 0.021%

founders and owners

No Comments

No Known Activations