INDEX

Explanations

listen

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

orting

-0.27

 Ð²ÐµÐº

-0.27

nug

-0.27

æĸ¹éĿ¢

-0.26

çľĭä¸įæĩĤ

-0.25

ooks

-0.25

orth

-0.24

æĲģ

-0.24

 myself

-0.24

 orthogonal

-0.24

POSITIVE LOGITS

 blossom

0.26

ultipartFile

0.25

å·®åĪ«

0.25

çıı

0.25

éĥĽ

0.24

ucas

0.24

Unified

0.24

è¦ģåģļåĪ°

0.24

 dubbed

0.24

upert

0.24

Activations Density 0.001%

listen

No Comments

No Known Activations