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

æĬĳ

-0.32

Ð²ÐµÐ½

-0.25

 breakup

-0.24

çªģçĦ¶

-0.24

å°½å¿«

-0.24

 starting

-0.23

her

-0.23

å¥¹çļĦ

-0.23

 most

-0.23

OK

-0.23

POSITIVE LOGITS

eway

0.28

åıįèĢĮ

0.25

Politics

0.25

 ['',

0.25

Rox

0.24

_residual

0.24

poo

0.24

RequestMethod

0.23

plx

0.23

 hereby

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.