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

ren

-0.29

åħ»

-0.29

aps

-0.28

**

-0.27

Temporary

-0.27

è¿Ń

-0.26

Ren

-0.26

acity

-0.25

osite

-0.25

çŁŃ

-0.25

POSITIVE LOGITS

æīī

0.30

å®ķ

0.28

orris

0.27

GRAM

0.27

experiment

0.26

_GB

0.26

çªģçł´

0.25

Ø§Ø©

0.25

 Blazers

0.25

è§ĤéŁ³

0.25

Activations Density 0.004%

No Known Activations

This feature has no known activations.