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

 knocking

-0.26

 Hazel

-0.26

éĽķ

-0.25

 correlations

-0.25

cess

-0.24

asel

-0.24

anter

-0.23

äºĴåĪ©

-0.23

dzi

-0.23

eses

-0.23

POSITIVE LOGITS

å¤ĩ

0.30

è°±

0.29

åģı

0.26

ui

0.24

ga

0.24

åı£

0.24

æĹı

0.24

æ³Ħéľ²

0.24

ypass

0.24

tan

0.24

Activations Density 0.023%

No Known Activations

This feature has no known activations.