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

worthy

-0.26

virt

-0.26

rin

-0.26

 merger

-0.26

ç©·

-0.25

çĿ¹

-0.24

 Intellectual

-0.24

Intel

-0.24

å¤©çĶŁ

-0.24

 adul

-0.23

POSITIVE LOGITS

asts

0.27

uffles

0.26

ncy

0.26

laps

0.26

Plans

0.25

itions

0.25

 getActivity

0.25

ileo

0.25

ats

0.24

enko

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.