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

æīĵå¥½

-0.29

py

-0.29

tion

-0.29

agon

-0.28

æł¸å¿ĥæĬĢæľ¯

-0.26

æĶ¶åī²

-0.26

achine

-0.26

 negatives

-0.25

flex

-0.25

cot

-0.25

POSITIVE LOGITS

:\/\/

0.27

çīł

0.25

èŃ¬

0.25

į°

0.24

 addCriterion

0.24

TimeStamp

0.24

asio

0.24

 convinc

0.24

 uphol

0.23

 engraved

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.