INDEX

Explanations

method

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 moderator

-0.26

ToAdd

-0.26

å¯¹å¾ħ

-0.26

 handles

-0.25

 Handles

-0.25

å¤ĦçĲĨ

-0.25

 handleMessage

-0.25

æ¯ĭ

-0.25

alus

-0.25

ëħĢ

-0.24

POSITIVE LOGITS

pu

0.29

äº¬

0.28

åĩºåİĤ

0.28

hum

0.26

Net

0.26

pac

0.26

Net

0.25

pac

0.25

 patriot

0.25

acci

0.25

Activations Density 1.701%

method

No Comments

No Known Activations