INDEX

Explanations

informal conversation snippets

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

Verse

-0.27

 Concord

-0.27

åĲİåı°

-0.26

éĢīåĿĢ

-0.26

Be

-0.26

 Procedure

-0.26

extract

-0.25

 Dictionary

-0.25

ophobia

-0.25

 abdomen

-0.25

POSITIVE LOGITS

legen

0.30

éĺį

0.29

 specs

0.28

legt

0.27

éĵĿ

0.26

riott

0.26

 aluminium

0.26

ÅŁtÄ±r

0.25

specs

0.25

croll

0.25

Activations Density 0.093%

informal conversation snippets

No Comments

No Known Activations