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

 chall

-0.30

_gradients

-0.29

morph

-0.26

 prer

-0.26

 Chall

-0.26

idan

-0.26

hic

-0.25

 challenge

-0.24

mah

-0.24

ç¦Ģ

-0.24

POSITIVE LOGITS

nnen

0.25

thes

0.25

 Plant

0.25

 curator

0.24

abo

0.24

ender

0.23

Ã§o

0.23

ending

0.23

 plant

0.23

å²Ļ

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.