INDEX

Explanations

on

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

 Lair

-0.30

åķĨä¼ļ

-0.26

çļĦåľ°æĸ¹

-0.26

quot

-0.26

oid

-0.25

urn

-0.24

åľ°æĸ¹

-0.24

åıŃ

-0.24

äº¤éĢļè¿Ĳè¾ĵ

-0.24

udio

-0.24

POSITIVE LOGITS

 Prob

0.27

NOWLED

0.26

 prob

0.24

 probabil

0.24

æİª

0.24

Prob

0.24

apel

0.24

åĿ¦

0.24

 Frame

0.23

 RegExp

0.23

Activations Density 0.002%

on

No Comments

No Known Activations