INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_35.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.35.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ionate

-0.27

 tiáº¿n

-0.27

vais

-0.26

 flavour

-0.26

 Ð²ÐºÑĥÑģ

-0.24

 Carlson

-0.24

Labour

-0.24

 Swinger

-0.24

mage

-0.24

esda

-0.24

POSITIVE LOGITS

æĶ¯

0.30

im

0.30

ck

0.29

pl

0.29

andi

0.28

De

0.28

è¶¾

0.27

azy

0.27

<|endoftext|>

0.27

etch

0.26

Activations Density 3.688%

No Known Activations

This feature has no known activations.