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

æľŃ

-0.29

è´Ŀå°Ķ

-0.27

 Birch

-0.26

éĿĴéĵľ

-0.26

arn

-0.26

 matters

-0.25

 duplicated

-0.25

 Review

-0.25

ç¶Ń

-0.24

ä¸įä¹ħ

-0.24

POSITIVE LOGITS

åħ¬çĽĬæĢ§

0.29

rix

0.27

ç©¿è¡£

0.27

è¶ħçº§

0.26

lider

0.26

tep

0.25

_Channel

0.25

rio

0.25

ariate

0.24

ICC

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.