INDEX

Explanations

No Explanations Found

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Theodore

-0.27

orical

-0.26

pell

-0.26

æĲºå¸¦

-0.25

 Podesta

-0.25

é¢Ħæµĭ

-0.25

åī§

-0.24

ehr

-0.24

 unemployed

-0.24

è·Ħ

-0.24

POSITIVE LOGITS

_accessor

0.28

VIR

0.26

oval

0.26

[]

0.26

iew

0.26

eler

0.25

colon

0.25

 colon

0.25

åį´æĺ¯

0.24

.builder

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.