INDEX

Explanations

:

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

ç¼Ł

-0.26

è£ķ

-0.26

ayah

-0.26

çŀ³

-0.25

-auto

-0.25

oreach

-0.25

ÙĪÙĥ

-0.24

ÑĩÐµ

-0.24

ħį

-0.23

ampil

-0.23

POSITIVE LOGITS

 site

0.27

mens

0.26

itlement

0.26

çĽ¾

0.26

 enormously

0.26

Rug

0.25

 Works

0.25

Gow

0.25

 unreal

0.24

éĢĤåº¦

0.24

Activations Density 0.095%

:

No Comments

No Known Activations