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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 exchanging

-0.27

wr

-0.27

Wrapped

-0.27

alley

-0.26

inidad

-0.26

elter

-0.25

(java

-0.25

ä¹°åĪ°

-0.24

 dangerously

-0.24

 Alternatively

-0.24

POSITIVE LOGITS

è¯Ńæĸĩ

0.29

ãĤŃãĥ£ãĥ³

0.28

ban

0.28

amb

0.27

æĸĩåŃ¦

0.27

é¹¤

0.26

-bordered

0.26

å¿«ä¹Ĳ

0.25

ordan

0.25

duck

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.