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

ogr

-0.27

é¥Ńèıľ

-0.26

bay

-0.26

 jeden

-0.25

facts

-0.25

è··

-0.25

å®ĺ

-0.24

éĩĳæ²Ļ

-0.24

é¢

-0.24

CDC

-0.24

POSITIVE LOGITS

åĬ¡

0.25

IBE

0.25

 Jenner

0.25

gable

0.24

ibe

0.24

è§£åĨ³æĸ¹æ¡Ī

0.24

éĻĪè¿°

0.24

éĺĦ

0.24

nhi

0.24

Ib

0.24

Activations Density 0.015%

No Known Activations

This feature has no known activations.