INDEX

Explanations

prize

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

åĽ½åľŁ

-0.27

 Patch

-0.26

UTION

-0.26

sap

-0.26

 TMPro

-0.25

tam

-0.24

eos

-0.24

sdale

-0.24

ebin

-0.24

 Treat

-0.24

POSITIVE LOGITS

igraph

0.26

++

0.26

mat

0.26

æĲº

0.25

holder

0.24

)}>

0.24

it

0.23

çķħ

0.23

Activations Density 0.211%

prize

No Comments

No Known Activations