INDEX

Explanations

Code and dashes

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

ain

-0.27

className

-0.24

åĿį

-0.24

align

-0.23

_some

-0.23

ownt

-0.23

queryString

-0.23

-main

-0.23

 Griffin

-0.23

-description

-0.23

POSITIVE LOGITS

 consulted

0.27

ç®

0.26

åĬĽåŃ¦

0.25

jar

0.24

apult

0.24

dur

0.24

ANT

0.24

 horn

0.24

ments

0.24

 presence

0.24

Activations Density 0.000%

Code and dashes

No Comments

No Known Activations