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

ringe

-0.27

inte

-0.27

 backlash

-0.26

leting

-0.26

eing

-0.26

 inputs

-0.25

éķ£

-0.25

å¿ħ

-0.24

inputs

-0.24

phin

-0.24

POSITIVE LOGITS

kop

0.29

ç®ĹäºĨ

0.26

 samo

0.25

IRR

0.25

ris

0.24

å©ļ

0.24

Discovery

0.24

éŁ³

0.24

_intr

0.24

')[

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.