INDEX

Explanations

No Explanations Found

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

esthetic

-0.28

 prÃ©cÃ©dent

-0.28

 factorial

-0.25

 flirt

-0.25

DT

-0.25

åĿ¦

-0.25

ArgsConstructor

-0.24

åŀ«

-0.23

é«ĺå³°æľŁ

-0.23

.Ed

-0.23

POSITIVE LOGITS

 outs

0.29

æ´Ĺè¡£

0.29

bserv

0.25

å¤ļæł·

0.25

 stem

0.25

egan

0.25

æµı

0.25

bite

0.24

using

0.24

 spyOn

0.24

Activations Density 0.000%

No Comments

No Known Activations